Integration of a neural network assistant on programming into a digital educational platform

The article presents the results of the development and implementation of instrumental student support based on generative large language models (LLM) within a digital educational platform (DEP). The problems of this study are caused by the lack of operational methodological feedback in the process of mass programming training, especially at the initial stages of developing practical skills. The proposed solution is to create and integrate a neural network module that aggregates information about a learning task (condition, name, hidden tests, reference solution, etc.) to generate personalized pedagogical prompts aimed at step-by-step comprehension of mistakes made and their independent correction by students without directly giving the correct solution. The article describes in detail the service architecture, the principles of its integration into the task verification system, as well as mechanisms for validating model responses and protecting them from misuse or unfair use. The empirical base of the study includes the results of testing in the framework of intensive specialized shifts (mini-courses) “Kurchatov Codes” conducted for high school students, using quantitative methods of analyzing educational and behavioral data. It is shown that the use of a neural network assistant helps to increase student engagement, reduce cognitive and psychological barriers in finding and correcting mistakes, and leads to a statistically significant reduction in the routine burden on teaching staff while maintaining the pedagogical validity of training.

1. Yizhou Qian, Lehman J. Students’ misconceptions and other difficulties in introductory programming: A literature review. ACM Transactions on Computing Education (TOCE). 2017;18(1):1–24. DOI: 10.1145/3077618.

2. Anderson J. R., Corbett A. T., Koedinger K. R., Pelletier R. Cognitive tutors: Lessons learned. Journal of the Learning Sciences. 1995;4(2):167–207. DOI: 10.1207/s15327809jls0402_2.

3. Koedinger K. R., Anderson J. R., Hadley W. H., Mark M. A. Intelligent tutoring goes to school in the big city. International Journal of Artificial Intelligence in Education. 1997;8:30–43. DOI: 10.1184/R1/6470153.v1.

4. VanLehn K. The relative effectiveness of human tutoring, intelligent tutoring systems, and other tutoring systems. Educational Psychologist. 2011;46(4):197–221. DOI: 10.1080/00461520.2011.611369.

5. Murray T. An overview of intelligent tutoring system authoring tools: Updated analysis of the state of the art. In: Murray T., Blessing S. B., Ainsworth S. (eds) Authoring Tools for Advanced Technology Learning Environments. Dordrecht, Springer; 2003:491–544. DOI: 10.1007/978-94-017-0819-7_17.

6. Keuning H., Jeuring J., Heeren B. A systematic literature review of automated feedback generation for programming exercises. ACM Transactions on Computing Education (TOCE). 2018;19(1):1–43. DOI: 10.1145/3231711.

7. Ihantola P., Vihavainen A., Ahadi A., et al. Educational data mining and learning analytics in programming: Literature review and case studies. Proc. 2015 ITiCSE on Working Group Reports (ITICSE–WGR’15). 2015:41–63. DOI: 10.1145/2858796.2858798.

8. Luxton-Reilly A., Simon, Albluwi I., et al. Introductory programming: A systematic literature review. Proc. Companion of the 23rd Annual ACM Conf. on Innovation and Technology in Computer Science Education (ITiCSE 2018). 2018:55–106. DOI: 10.1145/3293881.3295779. EDN: TGGWVQ.

9. Edwards S. H. Improving student performance by evaluating how well students test their own programs. Journal on Educational Resources in Computing (JERIC). 2003;3(3):1–es. DOI: 10.1145/1029994.1029995.

10. Finnie-Ansley J., Denny P., Becker B. A., LuxtonReilly A., Prather J. The robots are coming: Exploring the implications of OpenAI Codex on introductory programming. Proc. 24th Australasian Computing Education Conf. (ACE’22). 2022:10–19. DOI: 10.1145/3511861.3511863.

11. Denny P., Leinonen J., Prather J., Luxton-Reilly A., Amarouche T., Becker B. A., Reeves B. N. Prompt problems: A new programming exercise for the generative AI era. Proc. 55th ACM Technical Symposium on Computer Science Education (SIGCSE 2024). 2024;1:296–302. DOI: 10.1145/3626252.3630909.

12. Kazemitabaar M., Chow J., Ma C. K. T., Ericson B. J., Weintrop D., Grossman T. Studying the effect of AI code generators on supporting novice learners in introductory programming. Proc. 2023 CHI Conf. on Human Factors in Computing Systems (CHI’23). 2023:1–23. DOI: 10.1145/3544548.3580919.

13. Prather J., Reeves B. N., Denny P., Becker B. A., Leinonen J., Luxton-Reilly A., Powell G., Finnie-Ansley J., Santos E. A. “It’s weird that it knows what I want”: Usability and interactions with Copilot for novice programmers. ACM Transactions on Computer-Human Interaction. 2023;31(1):1–31. DOI: 10.1145/3617367.

14. Becker B. A., Denny P., Finnie-Ansley J., LuxtonReilly A., Prather J., Santos E. A. Programming is hard — or at least it used to be: Educational opportunities and challenges of AI code generation. Proc. 54th ACM Technical Symposium on Computer Science Education (SIGCSE 2023). 2023;1:500–506. DOI: 10.1145/3545945.3569759.

15. Finnie-Ansley J., Denny P., Luxton-Reilly A., Santos E. A., Prather J., Becker B. A. My AI wants to know if this will be on the exam: Testing OpenAI’s Codex on CS2 programming exercises. Proc. 25th Australasian Computing Education Conf. (ACE’23). New York, NY, USA, Association for Computing Machinery; 2023:97–104. DOI: 10.1145/3576123.3576134.

16. Lewis P., Piktus A., Petroni F., et al. Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems. Proc. 34th Conf. on Neural Information Processing Systems (NEURIPS 2020). 2020;34:9459–9474. EDN: JPMMQE.

17. Vasilyev I. A., Kushnirenko A. G., Leonov A. G., Mashchenko K. A., Kholkina A. A., Shlyakhov A. V. Mirera digital educational platform as the basis of digital transformation of the educational process. New Educational Strategies in the Modern Information Space. Collection of Scientific Articles Based on the Materials of the Int. Scientific and Practical Conf. Saint Petersburg, SITC Asterion; 2023:140–144. (In Russian.) EDN: AEPIFI.

18. Yi Liu, Gelei Deng, Yuekang Li, et al. Prompt injection attack against LLM-integrated applications. 2023. DOI: 10.48550/arXiv.2306.05499.

19. Leonov A. G., Martynov N. S., Mashchenko K. A., Paremuzov M. S., Pchelin K. K., Shlyakhov A. V. Applications of large language models for digital educational platforms. SRISA Proceedings. 2025;15(2):9–15. (In Russian.) DOI: 10.25682/NIISI.2025.2.0001. EDN: WNMVHS.

20. MacQueen J. Some methods for classification and analysis of multivariate observations. Proc. 5th Berkeley Symposium on Mathematical Statistics and Probability. 1967;5.1:281–297.